mlsanityData to 7 Oct 2026

Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models

arXiv 2607.14049 ↗First posted 15 Jul 2026cs.AIcited by 0

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors occur, current interaction approaches typically involve re-generating another response that may make mistakes again, or users laboriously flag the faulty step in follow-up turns that may get responses <You are right, I made a mistake here> followed by similar errors recurring. To address this issue, we propose an efficient human intervention mechanism for precisely correcting reasoning errors in LLMs, termed Deep Interaction. Our approach enables direct editing of the original response, allowing erroneous parts to be corrected while preserving accurate reasoning steps. We refine the edited CoT into a distilled prompt, which then steers the LLM along the corrected reasoning path. Experimental results show that our method achieves over a 25% improvement in correction success rate and reduces token usage by approximately 40% on STEM tasks reasoning compared to baseline approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 50 of its 81 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

50 of 81 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations16 May
  2. 2025Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning23 Apr
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models12 Mar
  4. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs24 Apr
  5. 2023Towards Better Chain-of-Thought Prompting Strategies: A Survey8 Oct
  6. 2023Human-in-the-Loop through Chain-of-Thought10 Jun
  7. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct

Other references · 43

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2024Qwen2 Technical Reportcited by 2,076
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  8. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  9. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  10. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  11. 2024DeepSeek-V3 Technical Reportcited by 724
  12. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
31 more
  1. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Modelscited by 533
  2. 2025Humanity's Last Examcited by 467
  3. 2023Model Tells You What to Discard: Adaptive KV Cache Compression for LLMscited by 466
  4. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  5. 2024Alignment faking in large language modelscited by 316
  6. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  7. 2023A Survey of Reinforcement Learning from Human Feedbackcited by 259
  8. 2025Reasoning Models Can Be Effective Without Thinkingcited by 182
  9. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 146
  10. 2025Process Reward Models That Thinkcited by 118
  11. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  12. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  13. 2024SWE-Bench+: Enhanced Coding Benchmark for LLMscited by 95
  14. 2023LLMs cannot find reasoning errors, but can correct them given the error locationcited by 85
  15. 2023RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thoughtcited by 47
  16. 2023Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioningcited by 47
  17. 2025Reward Reasoning Modelcited by 47
  18. 2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinkingcited by 46
  19. 2024LLM-as-a-Judge & Reward Model: What They Can and Cannot Docited by 32
  20. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  21. 2025Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Modelscited by 18
  22. 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Modelscited by 15
  23. 2025Enhancing Reasoning through Process Supervision with Monte Carlo Tree Searchcited by 14
  24. 2025SafeWork-R1: Coevolving Safety and Intelligence under the AI-45circ Lawcited by 13
  25. 2023Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Modelscited by 12
  26. 2025An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoningcited by 12
  27. 2024GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluationcited by 10
  28. 2025LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questionscited by 8
  29. 2025CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedbackcited by 4
  30. 2025Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Modelscited by 3
  31. 2025A Report on the llms evaluating the high school questionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
  2. 2025Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
  3. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  4. 2025Reasoning Can Hurt the Inductive Abilities of Large Language Models
  5. 2026Beyond Model Scaling: Test-Time Intervention for Efficient Deep Reasoning
  6. 2025Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models
  7. 2024On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
  8. 2025The Challenge of Teaching Reasoning to LLMs Without RL or Distillation